© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2008
    Prev
    Next
    INDEX
    Explanations

    HTML element tags and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML or code snippets

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions or academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    super
    -1.44
     super
    -1.39
     Super
    -1.06
    Super
    -1.02
     SUPER
    -0.95
    SUPER
    -0.86
     супер
    -0.84
     súper
    -0.79
    超级
    -0.73
    uper
    -0.71
    POSITIVE LOGITS
    boxed
    0.92
    SourceChecksum
    0.87
    makeConstraints
    0.84
    ConstraintMaker
    0.82
    wpi
    0.77
     EconPapers
    0.68
    underline
    0.64
    memoized
    0.61
    bold
    0.61
     betweenstory
    0.60
    Activations Density 0.582%

    No Known Activations